Conference paper · 2023 · Open access

Model Conversion via Differentially Private Data-Free Distillation

Bochao Liu, Pengju Wang, Shikun Li, Dan Zeng, Shiming Ge

International Joint Conference on Artificial Intelligence, 2187–2195 · Published 1 August 2023 · DOI 10.24963/ijcai.2023/243

Open PDFView at the publisherCite this paper

In brief

“Model Conversion via Differentially Private Data-Free Distillation” is a 2023 conference paper by Bochao Liu and 4 co-authors, published in International Joint Conference on Artificial Intelligence. OpenAlex counts 10 citations as of 19 November 2026. It is open access: the full text is free to read at International Joint Conference on Artificial Intelligence.

Citations
10
Most cited in
2025 (4)
Field-weighted impact
0.63
References
55
Authors
5

Abstract

While massive valuable deep models trained on large-scale data have been released to facilitate the artificial intelligence community, they may encounter attacks in deployment which leads to privacy leakage of training data. In this work, we propose a learning approach termed differentially private data-free distillation (DPDFD) for model conversion that can convert a pretrained model (teacher) into its privacy-preserving counterpart (student) via an intermediate generator without access to training data. The learning collaborates three parties in a unified way. First, massive synthetic data are generated with the generator. Then, they are fed into the teacher and student to compute differentially private gradients by normalizing the gradients and adding noise before performing descent. Finally, the student is updated with these differentially private gradients and the generator is updated by taking the student as a fixed discriminator in an alternate manner. In addition to a privacy-preserving student, the generator can generate synthetic data in a differentially private way for other down-stream tasks. We theoretically prove that our approach can guarantee differential privacy and well convergence. Extensive experiments that significantly outperform other differentially private generative approaches demonstrate the effectiveness of our approach.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Liu, B., Wang, P., Li, S., Zeng, D., & Ge, S. (2023). Model Conversion via Differentially Private Data-Free Distillation. International Joint Conference on Artificial Intelligence, 2187–2195. https://doi.org/10.24963/ijcai.2023/243

MLA 9

Liu, Bochao, et al. “Model Conversion via Differentially Private Data-Free Distillation.” International Joint Conference on Artificial Intelligence, 2023, pp. 2187–2195. https://doi.org/10.24963/ijcai.2023/243.

Chicago

Liu, Bochao, Pengju Wang, Shikun Li, Dan Zeng, and Shiming Ge. 2023. “Model Conversion via Differentially Private Data-Free Distillation.” International Joint Conference on Artificial Intelligence: 2187–2195. https://doi.org/10.24963/ijcai.2023/243.

Harvard

Liu, B. et al. (2023) ‘Model Conversion via Differentially Private Data-Free Distillation’, International Joint Conference on Artificial Intelligence, pp. 2187–2195. doi:10.24963/ijcai.2023/243.

IEEE

B. Liu, P. Wang, S. Li, D. Zeng, and S. Ge, “Model Conversion via Differentially Private Data-Free Distillation,” International Joint Conference on Artificial Intelligence, pp. 2187–2195, 2023, doi: 10.24963/ijcai.2023/243.

BibTeX

@inproceedings{liu2023model,
  title     = {{Model Conversion via Differentially Private Data-Free Distillation}},
  author    = {Liu, Bochao and Wang, Pengju and Li, Shikun and Zeng, Dan and Ge, Shiming},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {2187--2195},
  doi       = {10.24963/ijcai.2023/243},
  url       = {https://doi.org/10.24963/ijcai.2023/243}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202311
202422
202544
202633

Its field-weighted citation impact is 0.63: it has been cited 0.63 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • model transformation
  • knowledge distillation
  • differential privacy
  • synthetic data generation
  • privacy-preserving deep learning
  • generative models

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Liu, B., Wang, P., Li, S., Zeng, D., & Ge, S. (2023). Model Conversion via Differentially Private Data-Free Distillation. International Joint Conference on Artificial Intelligence, 2187–2195. https://doi.org/10.24963/ijcai.2023/243

How many times has this paper been cited?

10 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at International Joint Conference on Artificial Intelligence: sign in and open the PDF from this page.

Who wrote this paper?

Bochao Liu, Pengju Wang, Shikun Li, Dan Zeng, Shiming Ge.

What is the DOI of this paper?

10.24963/ijcai.2023/243, permanently at https://doi.org/10.24963/ijcai.2023/243. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.